A new approach to fuzzy modeling

Euntai Kim, Minkee Park, Seunghwan Ji, Mignon Park

Research output: Contribution to journalArticle

360 Citations (Scopus)

Abstract

This paper proposes a new approach to fuzzy modeling. The suggested fuzzy model can express a given unknown system with a few fuzzy rules as well as Takagi and Sugeno's model [1], because it has the same structure as that of Takagi and Sugeno's model. It is also as easy to implement as Sugeno and Yasukawa's model [2] because its identification mimics the simple identification procedure of Sugeno and Yasukawa's model. The suggested algorithm is composed of two steps: coarse tuning and fine tuning. In coarse tuning, fuzzy C-regression model (FCRM) clustering is used [3], which is a modified version of fuzzy C-means (FCM) [4]. In fine tuning, gradient descent algorithm is used to precisely adjust parameters of the fuzzy model instead of nonlinear optimization methods used in other models. Finally, some examples are given to demonstrate the validity of this algorithm.

Original languageEnglish
Pages (from-to)328-337
Number of pages10
JournalIEEE Transactions on Fuzzy Systems
Volume5
Issue number3
DOIs
Publication statusPublished - 1997 Dec 1

Fingerprint

Fuzzy Modeling
Tuning
Fuzzy Model
Model
Descent Algorithm
Fuzzy C-means
Gradient Algorithm
Gradient Descent
Identification (control systems)
Nonlinear Optimization
Fuzzy Rules
Optimization Methods
Regression Model
Express
Clustering
Fuzzy rules
Unknown
Demonstrate

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Kim, Euntai ; Park, Minkee ; Ji, Seunghwan ; Park, Mignon. / A new approach to fuzzy modeling. In: IEEE Transactions on Fuzzy Systems. 1997 ; Vol. 5, No. 3. pp. 328-337.
@article{83483cb3352b4bf2b3288f9e4c18800e,
title = "A new approach to fuzzy modeling",
abstract = "This paper proposes a new approach to fuzzy modeling. The suggested fuzzy model can express a given unknown system with a few fuzzy rules as well as Takagi and Sugeno's model [1], because it has the same structure as that of Takagi and Sugeno's model. It is also as easy to implement as Sugeno and Yasukawa's model [2] because its identification mimics the simple identification procedure of Sugeno and Yasukawa's model. The suggested algorithm is composed of two steps: coarse tuning and fine tuning. In coarse tuning, fuzzy C-regression model (FCRM) clustering is used [3], which is a modified version of fuzzy C-means (FCM) [4]. In fine tuning, gradient descent algorithm is used to precisely adjust parameters of the fuzzy model instead of nonlinear optimization methods used in other models. Finally, some examples are given to demonstrate the validity of this algorithm.",
author = "Euntai Kim and Minkee Park and Seunghwan Ji and Mignon Park",
year = "1997",
month = "12",
day = "1",
doi = "10.1109/91.618271",
language = "English",
volume = "5",
pages = "328--337",
journal = "IEEE Transactions on Fuzzy Systems",
issn = "1063-6706",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

A new approach to fuzzy modeling. / Kim, Euntai; Park, Minkee; Ji, Seunghwan; Park, Mignon.

In: IEEE Transactions on Fuzzy Systems, Vol. 5, No. 3, 01.12.1997, p. 328-337.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new approach to fuzzy modeling

AU - Kim, Euntai

AU - Park, Minkee

AU - Ji, Seunghwan

AU - Park, Mignon

PY - 1997/12/1

Y1 - 1997/12/1

N2 - This paper proposes a new approach to fuzzy modeling. The suggested fuzzy model can express a given unknown system with a few fuzzy rules as well as Takagi and Sugeno's model [1], because it has the same structure as that of Takagi and Sugeno's model. It is also as easy to implement as Sugeno and Yasukawa's model [2] because its identification mimics the simple identification procedure of Sugeno and Yasukawa's model. The suggested algorithm is composed of two steps: coarse tuning and fine tuning. In coarse tuning, fuzzy C-regression model (FCRM) clustering is used [3], which is a modified version of fuzzy C-means (FCM) [4]. In fine tuning, gradient descent algorithm is used to precisely adjust parameters of the fuzzy model instead of nonlinear optimization methods used in other models. Finally, some examples are given to demonstrate the validity of this algorithm.

AB - This paper proposes a new approach to fuzzy modeling. The suggested fuzzy model can express a given unknown system with a few fuzzy rules as well as Takagi and Sugeno's model [1], because it has the same structure as that of Takagi and Sugeno's model. It is also as easy to implement as Sugeno and Yasukawa's model [2] because its identification mimics the simple identification procedure of Sugeno and Yasukawa's model. The suggested algorithm is composed of two steps: coarse tuning and fine tuning. In coarse tuning, fuzzy C-regression model (FCRM) clustering is used [3], which is a modified version of fuzzy C-means (FCM) [4]. In fine tuning, gradient descent algorithm is used to precisely adjust parameters of the fuzzy model instead of nonlinear optimization methods used in other models. Finally, some examples are given to demonstrate the validity of this algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0031208215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031208215&partnerID=8YFLogxK

U2 - 10.1109/91.618271

DO - 10.1109/91.618271

M3 - Article

AN - SCOPUS:0031208215

VL - 5

SP - 328

EP - 337

JO - IEEE Transactions on Fuzzy Systems

JF - IEEE Transactions on Fuzzy Systems

SN - 1063-6706

IS - 3

ER -